

这是做钢笔画风格的lora,训练图用了83张训练图,
底模用的是CounterfeitV30_v30.safetensors,尺寸是512x768,描述词简单描述就好了,
例如树, 凳, 单色, 草, 户外, 坐, 独奏, 帽子, 1girl, 传统媒体, 风景...
因为训练图大多都是用的是户外场景图,所以出图出户外场景效果比较好,
我试了其他偏2次元风格的大模型也合适,权重调看着调就好;
The following is machine translated
This is to do the pen drawing style lora, the training map used 83 training maps , the
The base model used is CounterfeitV30_v30.safetensors, the size is 512x768, the descriptors are simple to describe.
For example tree, stool, monochrome, grass, outdoor, sitting, solo, hat, 1girl, traditional media, landscape...
Since most of the training maps are of outdoor scenes, it's better to map out outdoor scenes.
I tried other big models that favored the 2-dimensional style that also fit, and the weights tuned to look at the tuning;
1. 转载模型仅供学习与交流分享,其版权及最终解释权归原作者。
2. 模型原作者如需认领模型,请通过官方渠道联系海艺AI工作人员进行认证。我们致力于保护每一位创作者的权益。 点击去认领
